爬取”药智数据”网站下疾病分类与代码的所有疾病名称

整体代码如下：

import requests
import lxml.html
import chardet
import pymongo

# MongoDB数据库初始化，小批量插入数据
def mongodb(content_list):
    connection = pymongo.MongoClient()
    db = connection.Disease_classification
    collection = db.disease
    collection.insert(content_list)

# 对每个url获取小批量数据
def page_until_dict(source):
    selector = lxml.html.fromstring(source)
    code_list = selector.xpath('//div[@class="main"]/div[@class="offset-top table-list"]/table[@class="table table-striped"]/tbody/tr/th/text()')
    name_list = selector.xpath('//div[@class="main"]/div[@class="offset-top table-list"]/table[@class="table table-striped"]/tbody/tr/td[2]/text()')
    english_name_list = selector.xpath('//div[@class="main"]/div[@class="offset-top table-list"]/table[@class="table table-striped"]/tbody/tr/td[3]/text()')
    content_list = []
    for i in range(len(code_list)):
        content_list.append({'疾病编码':code_list[i],'疾病名称':name_list[i],'疾病名称（英文）':english_name_list[i]})   
    mongodb(content_list)

# 定义主函数
def main():
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36'}
    url_list = ["https://db.yaozh.com/icd?p={}&pageSize=30".format(str(i)) for i in range(1,8)]
    for url in range(len(url_list)):
        r = requests.get(url_list[url],headers=headers)
        r.encoding = chardet.detect(r.content)['encoding']
        source = r.text
        page_until_dict(source)
        
if __name__ == '__main__':
    main()

最终存入数据库如下：